Industrial Engineering & Management

Fuzzy DEMATEL and Fuzzy Binary Logistic Regression with Simulated Annealing Optimization for Risk Analysis and Mitigation in Industrial Projects in East Africa

Abstract

Hailu Worku*

Risk analysis and mitigation is a crucial step in the management of industrial projects, especially in developing regions such as East Africa, where the challenges and opportunities are more diverse and dynamic. This paper proposes a novel approach for risk analysis and mitigation in industrial projects in East Africa using fuzzy DEMATEL (Decision Making Trial and Evaluation Laboratory) and fuzzy binary logistic regression with simulated annealing optimization. The paper identifies six categories of risk factors for industrial projects based on literature review and expert opinions: Production and technical risks, market and customer risks, financial and economic risks, legal and regulatory risks, environmental and social risks, and human and organizational risks. The paper applies fuzzy DEMATEL method to evaluate the relative importance and influence of each risk factor on each category using linguistic terms that are converted into triangular fuzzy numbers. The paper also classifies the risk factors into four groups based on their prominence and relation degree: Cause group, effect group, cause-effect group, and independent group. The paper constructs an IP (Impact and Probability) table to rank the risk factors based on their impact and probability scores obtained from expert opinions. The paper uses fuzzy binary logistic regression to predict the probability of each level of risk (low, medium, high) for each risk factor based on its impact and probability scores. Finally, the paper uses simulated annealing optimization algorithm to minimize the probability of high level of risk for the project by adjusting the impact and probability scores of the risk factors. The paper presents a case study of an industrial project in East Africa to illustrate the application and effectiveness of the proposed approach. The paper discusses the implications and limitations of the proposed approach and suggests directions for future research.